Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 6068
    Prev
    Next
    INDEX
    Explanations

    function declarations and related elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ripar
    -0.53
    /**
    
    -0.52
    పు
    -0.48
     Bunk
    -0.48
    abol
    -0.47
    DoubleQuotes
    -0.46
    Inform
    -0.46
     individualism
    -0.46
    лен
    -0.45
    Execu
    -0.44
    POSITIVE LOGITS
     BoxDecoration
    0.87
    CloseOperation
    0.80
    ArrowToggle
    0.79
    tvguidetime
    0.73
     مشين
    0.73
    migrationBuilder
    0.71
    mybatisplus
    0.69
    DockStyle
    0.68
    脚注の使い方
    0.65
    melons
    0.64
    Activations Density 0.162%

    No Known Activations